We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
NRF Thuthuka Project: Microplastics Removal from Wastewater using Machine Learning Optimization (TTK240430216739)
Summary
Researchers proposed using artificial neural networks to optimize ultrasonication and membrane filtration for removing microplastics from urban wastewater, aiming to develop machine learning-enhanced treatment strategies that improve removal efficiency beyond what conventional wastewater plants achieve.
Increased microplastics contamination in wastewater is a challenge to the environment and public health. The removal of these pollutants requires innovative strategies for effective mitigation. This study aims to employ artificial neural network to optimize two promising microplastics removal methods from the urban water cycle: ultrasonication and membrane filtration. The project's overall objective is to advance sustainable technologies that supplement the efficacy of microplastics extraction from wastewater, addressing the environmental consequences. Leveraging ML, this research aims to optimize ultrasonication parameters and membrane filtration techniques while integrating interdisciplinary datasets to strengthen the robustness and applicability of ML models. A better understanding of the interplay between operational parameters and environmental impacts is anticipated by merging ML with the optimization processes. Such interdisciplinary (artificial intelligence-enabled prediction and optimization, chemical engineering, chemistry, and environmental science) measures can enhance microplastics removal efficiency and mitigate environmental harm, consequently enabling sustainable technologies to address microplastics pollution in wastewater. The research represents an important stride towards a data-driven paradigm in microplastics management, aligning with the following key United Nations Sustainable Development Goals: 6(clean water and sanitation), 11 (sustainable cities and communities), 12 (responsible consumption and production), 14 (life below water), and 15 (life on land). Furthermore, the project strives to support South African black female Chemical Engineering Hons, Masters, and Doctoral students, thus creating a pipeline of academic talent through rigorous academic training and development. These students are expected to find employment within Assistant Lecturer, Research Assistant, nGAP, andpost-doctoral research fellow positions.
Sign in to start a discussion.
More Papers Like This
NRF Thuthuka Project: Microplastics Removal from Wastewater using Machine Learning Optimization (TTK240430216739)
This project aimed to use machine learning to optimize two microplastic removal methods—ultrasonication and membrane filtration—from urban wastewater, leveraging artificial neural networks to identify optimal operating conditions for sustainable treatment at scale.
Design of an Efficient Model for Microplastic Removal in Wastewater using Advanced Filtration, Nanotechnology, and Bioremediation
This paper proposed an advanced machine learning model to design and optimize microplastic removal in wastewater treatment, using process parameters to predict removal efficiency. The intelligent model outperformed conventional design approaches in predicting treatment outcomes.
Revealing the removal behavior of five neglected microplastics in coagulation-ultrafiltration processes: Insights from experiments and predictive modeling
Researchers combined laboratory experiments with artificial neural network modeling to study how five commonly overlooked types of microplastics are removed during drinking water treatment. They found that coagulation alone removed 37-56% of the microplastics, while adding ultrafiltration removed virtually all remaining particles. The study provides new insights into the chemical and physical interactions that drive microplastic removal, which could help optimize water treatment processes.
A Review on Applications of Artificial Intelligence in Wastewater Treatment
This review summarizes how artificial intelligence models are being applied to improve wastewater treatment processes, including the removal of microplastics and other pollutants. Researchers found that machine learning and neural networks can effectively predict treatment efficiency, optimize operations, and reduce energy costs. The study suggests that AI-driven approaches could make water treatment systems more adaptive and cost-effective in handling emerging contaminants.
An Application of Ultrasonic Waves in the Pretreatment of Biological Sludge in Urban Sewage and Proposing an Artificial Neural Network Predictive Model of Concentration
This paper is not about microplastics; it investigates how ultrasonic waves at different frequencies and durations improve hydrolysis, stabilization, and dewatering of activated sludge from urban wastewater treatment plants, using artificial neural networks to model outcomes.